PlantVLM-Edge：量化视觉语言模型让边缘设备离线诊断作物健康
PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis
把 Qwen3-VL-2B 量化后塞进 Jetson，离线就能问作物病害和虫害，4-bit 只损失 1.4% 质量，种植者没网也能用。
论文提出 PlantVLM-Edge，一个可完全在边缘设备上离线运行的量化视觉语言框架，用于对话式作物健康诊断。框架与骨干无关，作者用 Qwen3-VL-2B 和 LLaVA-1.5-7B 两种 VLM、四种量化方案验证，并部署在 NVIDIA Jetson AGX Orin 上。4-bit AWQ 量化在植物病害和虫害两个诊断领域均保留 98.6% 的全精度回答质量，同时将 2B 骨干的权重内存减少 49%。最紧凑版本只需 2.01 GiB 权重内存，首 token 延迟约 0.12 秒，64 token 诊断回复在 0.78 秒内完成，全程无需云连接。
PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis
Timely and accurate crop health diagnosis is essential for sustainable agricultural production, yet accurate diagnosis often requires expert knowledge that is not readily available. Recent vision-language models (VLMs) have demonstrated remarkable capabilities in visual understanding, reasoning, and natural-language interaction, creating new opportunities for intelligent crop health assessment. However, deploying VLMs on resource-constrained devices remains challenging due to their substantial computational and memory requirements. This paper presents PlantVLM-Edge, a quantized vision-language framework for conversational crop health diagnosis that can run entirely on resource-constrained edge devices. PlantVLM-Edge combines agricultural domain adaptation, post-training quantization, and on-device serving with an offline chat interface, allowing growers to ask open-ended questions and receive diagnoses, symptom explanations, and management guidance without cloud connectivity. The framework is backbone-agnostic: we validate it with two different VLM types with varying scale and architecture (Qwen3-VL-2B and LLaVA-1.5-7B), four quantization schemes, and two diagnostic domains (plant diseases and insect pests), and we deploy all variants on an NVIDIA Jetson AGX Orin. Eight-bit quantization affects answer quality minimally relative to the full-precision model, and 4-bit activation-aware weight quantization (AWQ) retains 98.6% of full-precision answer quality on both domains while reducing the weight memory of the 2B backbone by 49%. In its most compact form, PlantVLM-Edge requires 2.01 GiB of weight memory, returns its first token in about 0.12 s, and completes a 64-token diagnostic response in 0.78 s. These results demonstrate that timely and accurate crop health diagnosis is practical on edge devices, providing a foundation for next-generation crop monitoring and decision support systems.